Massively Multilingual Neural Machine Translation
This work advances machine translation by enabling more languages to be supported efficiently, though it is incremental in scaling up existing multilingual NMT approaches.
The paper tackles the challenge of scaling multilingual neural machine translation to support up to 102 languages in a single model, showing that such massively multilingual models outperform previous state-of-the-art in low-resource settings and surpass strong bilingual baselines on large-scale datasets.
Multilingual neural machine translation (NMT) enables training a single model that supports translation from multiple source languages into multiple target languages. In this paper, we push the limits of multilingual NMT in terms of number of languages being used. We perform extensive experiments in training massively multilingual NMT models, translating up to 102 languages to and from English within a single model. We explore different setups for training such models and analyze the trade-offs between translation quality and various modeling decisions. We report results on the publicly available TED talks multilingual corpus where we show that massively multilingual many-to-many models are effective in low resource settings, outperforming the previous state-of-the-art while supporting up to 59 languages. Our experiments on a large-scale dataset with 102 languages to and from English and up to one million examples per direction also show promising results, surpassing strong bilingual baselines and encouraging future work on massively multilingual NMT.